Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    subscribe actions in text

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to subscription

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.73
    pher
    -0.72
    prototype
    -0.71
    stood
    -0.71
    flies
    -0.70
    dfx
    -0.69
    esan
    -0.67
    wikipedia
    -0.66
    iage
    -0.66
    nered
    -0.61
    POSITIVE LOGITS
     Subscribe
    1.02
    Subscribe
    0.97
     subscribe
    0.85
    Interstitial
    0.85
     subscribers
    0.79
    ickets
    0.78
     Newsletter
    0.74
     subscriptions
    0.73
     subscribing
    0.72
     Sign
    0.70
    Act Density 0.010%

    No Known Activations